mercurial/setdiscovery.py

push: stop independent usage of bundle2 in syncphase (issue4454)

The phase-syncing code was using bundle2 if the remote supported it. It was
doing so without regard to bundle2 activation on the client. Moreover, the
phase push is now properly included in the unified bundle2 push, so having extra
code in syncphase should be useless. If the remote is bundle2-enabled, the
phases should already be synced.

The buggy verification code was leading to a crash when a 3.2 client was pushing
to a 3.1 server. The real bundle2 path detected that their versions were
incompatible, but the syncphase code failed to, sending an incompatible bundle2
to the server.

We drop the useless and buggy code as a result. The "else" clause is
de-indented in the process.

# setdiscovery.py - improved discovery of common nodeset for mercurial
#
# Copyright 2010 Benoit Boissinot <[e-mail]>
# and Peter Arrenbrecht <[e-mail]>
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.
"""
Algorithm works in the following way. You have two repository: local and
remote. They both contains a DAG of changelists.

The goal of the discovery protocol is to find one set of node *common*,
the set of nodes shared by local and remote.

One of the issue with the original protocol was latency, it could
potentially require lots of roundtrips to discover that the local repo was a
subset of remote (which is a very common case, you usually have few changes
compared to upstream, while upstream probably had lots of development).

The new protocol only requires one interface for the remote repo: `known()`,
which given a set of changelists tells you if they are present in the DAG.

The algorithm then works as follow:

 - We will be using three sets, `common`, `missing`, `unknown`. Originally
 all nodes are in `unknown`.
 - Take a sample from `unknown`, call `remote.known(sample)`
   - For each node that remote knows, move it and all its ancestors to `common`
   - For each node that remote doesn't know, move it and all its descendants
   to `missing`
 - Iterate until `unknown` is empty

There are a couple optimizations, first is instead of starting with a random
sample of missing, start by sending all heads, in the case where the local
repo is a subset, you computed the answer in one round trip.

Then you can do something similar to the bisecting strategy used when
finding faulty changesets. Instead of random samples, you can try picking
nodes that will maximize the number of nodes that will be
classified with it (since all ancestors or descendants will be marked as well).
"""

from node import nullid
from i18n import _
import random
import util, dagutil

def _updatesample(dag, nodes, sample, always, quicksamplesize=0):
    # if nodes is empty we scan the entire graph
    if nodes:
        heads = dag.headsetofconnecteds(nodes)
    else:
        heads = dag.heads()
    dist = {}
    visit = util.deque(heads)
    seen = set()
    factor = 1
    while visit:
        curr = visit.popleft()
        if curr in seen:
            continue
        d = dist.setdefault(curr, 1)
        if d > factor:
            factor *= 2
        if d == factor:
            if curr not in always: # need this check for the early exit below
                sample.add(curr)
                if quicksamplesize and (len(sample) >= quicksamplesize):
                    return
        seen.add(curr)
        for p in dag.parents(curr):
            if not nodes or p in nodes:
                dist.setdefault(p, d + 1)
                visit.append(p)

def _setupsample(dag, nodes, size):
    if len(nodes) <= size:
        return set(nodes), None, 0
    always = dag.headsetofconnecteds(nodes)
    desiredlen = size - len(always)
    if desiredlen <= 0:
        # This could be bad if there are very many heads, all unknown to the
        # server. We're counting on long request support here.
        return always, None, desiredlen
    return always, set(), desiredlen

def _takequicksample(dag, nodes, size, initial):
    always, sample, desiredlen = _setupsample(dag, nodes, size)
    if sample is None:
        return always
    if initial:
        fromset = None
    else:
        fromset = nodes
    _updatesample(dag, fromset, sample, always, quicksamplesize=desiredlen)
    sample.update(always)
    return sample

def _takefullsample(dag, nodes, size):
    always, sample, desiredlen = _setupsample(dag, nodes, size)
    if sample is None:
        return always
    # update from heads
    _updatesample(dag, nodes, sample, always)
    # update from roots
    _updatesample(dag.inverse(), nodes, sample, always)
    assert sample
    sample = _limitsample(sample, desiredlen)
    if len(sample) < desiredlen:
        more = desiredlen - len(sample)
        sample.update(random.sample(list(nodes - sample - always), more))
    sample.update(always)
    return sample

def _limitsample(sample, desiredlen):
    """return a random subset of sample of at most desiredlen item"""
    if len(sample) > desiredlen:
        sample = set(random.sample(sample, desiredlen))
    return sample

def findcommonheads(ui, local, remote,
                    initialsamplesize=100,
                    fullsamplesize=200,
                    abortwhenunrelated=True):
    '''Return a tuple (common, anyincoming, remoteheads) used to identify
    missing nodes from or in remote.
    '''
    roundtrips = 0
    cl = local.changelog
    dag = dagutil.revlogdag(cl)

    # early exit if we know all the specified remote heads already
    ui.debug("query 1; heads\n")
    roundtrips += 1
    ownheads = dag.heads()
    sample = _limitsample(ownheads, initialsamplesize)
    # indices between sample and externalized version must match
    sample = list(sample)
    if remote.local():
        # stopgap until we have a proper localpeer that supports batch()
        srvheadhashes = remote.heads()
        yesno = remote.known(dag.externalizeall(sample))
    elif remote.capable('batch'):
        batch = remote.batch()
        srvheadhashesref = batch.heads()
        yesnoref = batch.known(dag.externalizeall(sample))
        batch.submit()
        srvheadhashes = srvheadhashesref.value
        yesno = yesnoref.value
    else:
        # compatibility with pre-batch, but post-known remotes during 1.9
        # development
        srvheadhashes = remote.heads()
        sample = []

    if cl.tip() == nullid:
        if srvheadhashes != [nullid]:
            return [nullid], True, srvheadhashes
        return [nullid], False, []

    # start actual discovery (we note this before the next "if" for
    # compatibility reasons)
    ui.status(_("searching for changes\n"))

    srvheads = dag.internalizeall(srvheadhashes, filterunknown=True)
    if len(srvheads) == len(srvheadhashes):
        ui.debug("all remote heads known locally\n")
        return (srvheadhashes, False, srvheadhashes,)

    if sample and len(ownheads) <= initialsamplesize and util.all(yesno):
        ui.note(_("all local heads known remotely\n"))
        ownheadhashes = dag.externalizeall(ownheads)
        return (ownheadhashes, True, srvheadhashes,)

    # full blown discovery

    # own nodes where I don't know if remote knows them
    undecided = dag.nodeset()
    # own nodes I know we both know
    common = set()
    # own nodes I know remote lacks
    missing = set()

    # treat remote heads (and maybe own heads) as a first implicit sample
    # response
    common.update(dag.ancestorset(srvheads))
    undecided.difference_update(common)

    full = False
    while undecided:

        if sample:
            commoninsample = set(n for i, n in enumerate(sample) if yesno[i])
            common.update(dag.ancestorset(commoninsample, common))

            missinginsample = [n for i, n in enumerate(sample) if not yesno[i]]
            missing.update(dag.descendantset(missinginsample, missing))

            undecided.difference_update(missing)
            undecided.difference_update(common)

        if not undecided:
            break

        if full:
            ui.note(_("sampling from both directions\n"))
            sample = _takefullsample(dag, undecided, size=fullsamplesize)
            targetsize = fullsamplesize
        elif common:
            # use cheapish initial sample
            ui.debug("taking initial sample\n")
            sample = _takefullsample(dag, undecided, size=fullsamplesize)
            targetsize = fullsamplesize
        else:
            # use even cheaper initial sample
            ui.debug("taking quick initial sample\n")
            sample = _takequicksample(dag, undecided, size=initialsamplesize,
                                      initial=True)
            targetsize = initialsamplesize
        sample = _limitsample(sample, targetsize)

        roundtrips += 1
        ui.progress(_('searching'), roundtrips, unit=_('queries'))
        ui.debug("query %i; still undecided: %i, sample size is: %i\n"
                 % (roundtrips, len(undecided), len(sample)))
        # indices between sample and externalized version must match
        sample = list(sample)
        yesno = remote.known(dag.externalizeall(sample))
        full = True

    result = dag.headsetofconnecteds(common)
    ui.progress(_('searching'), None)
    ui.debug("%d total queries\n" % roundtrips)

    if not result and srvheadhashes != [nullid]:
        if abortwhenunrelated:
            raise util.Abort(_("repository is unrelated"))
        else:
            ui.warn(_("warning: repository is unrelated\n"))
        return (set([nullid]), True, srvheadhashes,)

    anyincoming = (srvheadhashes != [nullid])
    return dag.externalizeall(result), anyincoming, srvheadhashes